How to Use the Aha! MCP in LlamaIndex

Q: How do I configure LlamaIndex with the Aha! MCP Server?

Run pip install llama-index-tools-mcp. Initialize BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex index Aha! feature descriptions?

Yes. Your application calls listfeatures and embeds the returned text into your vector store. Users then run natural language queries against your product specs.

Q: Does LlamaIndex support creating new Aha! ideas?

Your FunctionAgent executes the createidea tool when it detects a missing concept during a semantic search. It formats the proposal and pushes it to the API.

Q: How do I filter which Aha! tools my MCP client can access?

Use the allowedtools parameter when setting up your connection. You restrict the agent to read-only operations like listreleases if you want to prevent accidental modifications.

Index your Aha! product roadmaps directly into LlamaIndex applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aha! MCP to LlamaIndex

Create your Vinkius account to connect Aha! to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Aha! with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index feature backlogs for semantic search

The `list_features` tool pulls your entire product backlog via MCP into LlamaIndex so you can embed the results. Instead of relying on exact keyword matches in the Aha! UI, your RAG application lets users search for concepts. A query about payment updates surfaces all related features even if they use different terminology. You combine this API data with internal design documents to create a unified knowledge base. When a user asks your FunctionAgent about a planned capability, it searches the vector store and returns an answer grounded in actual roadmapping data.

Query Aha! MCP Server release schedules

Executing `list_releases` feeds upcoming launch timelines straight into your index. Your LlamaIndex application maps these dates against the feature embeddings. Teams ask questions like what ships in Q3 and get accurate summaries. The agent uses `get_feature` to pull the specifics for any item flagged in that release window. It caches the API response in the vector store for future queries. You build a system that actually knows what your product team is doing.

Turn raw ideas into searchable context

Running `list_ideas` extracts unfiltered customer suggestions and product concepts from Aha!. LlamaIndex converts these text blocks into vectors. Product managers then run semantic queries to see if a newly requested feature already exists in the idea pool. If a gap exists, the FunctionAgent triggers `create_idea` to log the missing concept. The new entry immediately becomes part of your searchable index. You stop building duplicate features because your RAG application knows exactly what ideas are pending.

Setup guide

Set up Aha! MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Aha! MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Aha! tools.",
)
response = await agent.run("List recent Aha! data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Aha!. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Aha! now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Aha! MCP in LlamaIndex

Run `pip install llama-index-tools-mcp`. Initialize `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and pass the async tool list to your FunctionAgent.

Yes. Your application calls `list_features` and embeds the returned text into your vector store. Users then run natural language queries against your product specs.

Your FunctionAgent executes the `create_idea` tool when it detects a missing concept during a semantic search. It formats the proposal and pushes it to the API.

Use the `allowed_tools` parameter when setting up your connection. You restrict the agent to read-only operations like `list_releases` if you want to prevent accidental modifications.

Vinkius handles the authorization using a zero-trust architecture. Your strategic goals and release dates pass through an ephemeral V8 sandbox before hitting your vector store. Nothing leaks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript